Skip to content

Qwen2.5 72B Instruct on 2× RTX 3090: VRAM, speed and fit

Qwen2.5 72B Instruct at 3-bit runs on the 2× RTX 3090 with 32K of context at about 18 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on 2× RTX 3090 · 3-bit (Q3_K_M) · Ollama / LM Studio · Chat

GPU memory
44.8 GB
of 48.0 GB
Context
32K
auto
Speed
18 tok/s
14 when full
First reply
2.5 s
2K prompt

Where the memory goes

Model
33.1 GB
Context
10.0 GB
Overhead
1.7 GB
OS
0.0 GB
Free
3.2 GB
Memory
44.8 GB of 48.0 GB
Context
32K tokens · auto
Speed
18 tok/s · 14 when full
First reply
2.5 s for a 2K prompt
Running cost
$11/mo at home · $66/mo on a cloud 2× RTX A5000

Validation: Validated

What Qwen2.5 72B Instruct on 2× RTX 3090 was checked against
CheckTargetResultStatus
Fits in GPU memory48.0 GB usable44.8 GB neededPass
Headroom5% free3.2 GB free (7%)Pass
Context for chat16K or more32KPass
Writing speed15 tok/s or more18 tok/sPass
First replyunder 3 s, 2K prompt2.5 sPass

Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.

The setup

Model
Qwen2.5 72B Instruct
Parameters
72.7B
Precision
3-bit (Q3_K_M)
Context
32K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
2× RTX 3090
GPU can use
48.0 GB of 48.0 GB

Running cost

At home
$11/mo
500 W at the wall
Renting instead
$66/mo
2× RTX A5000 at $0.54/h

4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.

How to run it

llama.cpp
llama-server -hf bartowski/Qwen2.5-72B-Instruct-GGUF
vLLM
vllm serve Qwen/Qwen2.5-72B-Instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen2.5-72B-Instruct-4bit

Qwen2.5 72B Instruct on similar machines

  • RTX 3090Too big
  • RTX 4090Too big
  • Radeon AI PRO R9700Just misses
  • RTX 5090Just misses
  • 2× RTX 4090Runs
  • RTX PRO 5000 Blackwell 48 GBRuns
  • RTX 6000 AdaRuns
  • L40SRuns

All machines: Qwen2.5 72B Instruct VRAM requirements. Everything that runs here: what can the 2× RTX 3090 run?

Other models that run on 2× RTX 3090

Questions

Can Qwen2.5 72B Instruct run on 2× RTX 3090?

Qwen2.5 72B Instruct at 3-bit runs on the 2× RTX 3090 with 32K of context at about 18 tokens a second.

Report VR-0STGS70, calculated Nov 22, 2026 from published specs, not benchmarked.